Mis-Understanding Conditional Probability The infamous " Prosecutor's Fallacy " may creep in while dealing with Discriminative classification models. An idea of how to argue while a feature probability is ascertained subject to the presence of another feature. Special care must be taken to avoid any illogical derivation. Readers: Must do a bit of literature survey on this frequent and possible "Anomaly".
Majid Ahmad ,
I would go further and state two problems from this:
While the " Prosecutor's Fallacy " is straightforward to understand, the issue in a particular domain is more subtle and necessitates domain knowledge understanding of what is the correct postulation of the problem.
Dear Majid Ahmad ,
Prosecutor's fallacy DNA
The prosecutor's fallacy is a fallacy of statistical reasoning involving a test for an occurrence, such as a DNA match. ... At its heart, therefore, the fallacy involves assuming that the prior probability of a random match is equal to the probability that the defendant is innocent.
https://towardsdatascience.com/the-prosecutors-fallacy-cb0da4e9c039
Regards,
Shafagat
Hi. I hope the following website could help you: best wishes:
https://towardsdatascience.com/the-prosecutors-fallacy-cb0da4e9c039?gi=47cb9aa601da
Arturo Geigel You made a good point!
Everyone knows what it is, But that makes it prone to creep in.
- Badges
- Science topic